© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 22186
    Prev
    Next
    INDEX
    Explanations

    references to occupational safety and health regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DX
    -0.15
    ugging
    -0.15
    OpenGL
    -0.15
    989
    -0.14
    akedown
    -0.14
    Rx
    -0.14
    ibu
    -0.14
    993
    -0.14
     Tear
    -0.14
    asje
    -0.13
    POSITIVE LOGITS
    OSH
    0.32
     employer
    0.26
     employers
    0.25
     Occupational
    0.25
     workplace
    0.24
     hazard
    0.24
    OS
    0.23
     Hazard
    0.23
    Occup
    0.23
    (OS
    0.23
    Activations Density 0.028%

    No Known Activations